Active sampling with allocation q_j proportional to p_j to the 2/3 achieves tight regret sqrt(n/T) times norm of p to the 2/3 for known context distribution p, with improvement up to Theta(k to the 1/4) over passive sampling.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
A modular reduction from budget-constrained contextual bandits with adversarial contexts to unconstrained bandits via surrogate rewards, yielding improved guarantees and an efficient algorithm based on SquareCB.
A projection-based algorithm for COCO achieves O(log T) regret and O(log T) CCV for strongly convex losses and O(sqrt(T)) for convex losses by leveraging self-contracted curves.
Localized model averaging with covariate-dependent weights achieves asymptotic optimality and weight consistency for combining pre-trained models under a general loss framework.
Rényi entropy is subadditive on the majorization lattice for every α ∈ [0,∞] and supermodular for α ∈ {0} ∪ [1,∞]; Tsallis entropy is subadditive and supermodular for all α ∈ [0,∞).
New extended-variable relaxations are derived for CGMESP that generalize prior bounds for CMESP and binary D-optimality and are tested numerically inside branch-and-bound.
citing papers explorer
-
Active Context Selection Improves Simple Regret in Contextual Bandits
Active sampling with allocation q_j proportional to p_j to the 2/3 achieves tight regret sqrt(n/T) times norm of p to the 2/3 for known context distribution p, with improvement up to Theta(k to the 1/4) over passive sampling.
-
Constrained Contextual Bandits with Adversarial Contexts
A modular reduction from budget-constrained contextual bandits with adversarial contexts to unconstrained bandits via surrogate rewards, yielding improved guarantees and an efficient algorithm based on SquareCB.
-
Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction
A projection-based algorithm for COCO achieves O(log T) regret and O(log T) CCV for strongly convex losses and O(sqrt(T)) for convex losses by leveraging self-contracted curves.
-
Combining pre-trained models via localized model averaging
Localized model averaging with covariate-dependent weights achieves asymptotic optimality and weight consistency for combining pre-trained models under a general loss framework.
-
Geometry of R\'enyi Entropy on the Majorization Lattice
Rényi entropy is subadditive on the majorization lattice for every α ∈ [0,∞] and supermodular for α ∈ {0} ∪ [1,∞]; Tsallis entropy is subadditive and supermodular for all α ∈ [0,∞).
-
Extended-variable relaxations for the constrained generalized maximum-entropy sampling problem
New extended-variable relaxations are derived for CGMESP that generalize prior bounds for CMESP and binary D-optimality and are tested numerically inside branch-and-bound.